A retry layer for the HTTPX client: configurable retry behaviour with
exponential backoff for transient HTTP errors.

Integration package connecting Claude (Anthropic) APIs and LangChain.

This package contains the LangChain integrations with AWS, connecting
LangChain to AWS services such as Amazon Bedrock, SageMaker, Neptune and
Kendra.

LangChain Core contains the base abstractions that power the rest of the
LangChain ecosystem.

These abstractions are designed to be as modular and simple as possible.
Examples of these abstractions include those for language models, document
loaders, embedding models, vectorstores, retrievers, and more.

The benefit of having these abstractions is that any provider can implement the
required interface and then easily be used in the rest of the LangChain
ecosystem.

This package contains the LangChain integrations for OpenAI through their
openai SDK.

It provides chat models, LLMs, embeddings and tokenization helpers that let
the OpenAI and Azure OpenAI services be used as components in the LangChain
ecosystem.

This is a little HTTP/1.1 library written from scratch in Python,
heavily inspired by hyper-h2

LangGraph is a low-level orchestration framework for building, running and
managing stateful, multi-actor applications with large language models.

It models an application as a graph of nodes and edges with shared state,
adding durable execution with checkpointing, human-in-the-loop interaction,
streaming of tokens and intermediate steps, and time-travel debugging. This
package provides the core graph API (StateGraph), the Pregel runtime, the
functional API, channels and managed values shared across the LangGraph
ecosystem.

The LangGraph SDK provides synchronous and asynchronous Python clients for
interacting with the LangGraph API, exposing helpers for assistants, threads,
runs, crons and the persistent store.

Magika is an AI-powered file type detection tool. It uses a small
deep-learning model (a few MiB) to identify 200+ binary and textual
content types, typically within milliseconds on a single CPU.

This package provides the Python module and magika-python-client.
The primary magika command is the separate Rust CLI and is not
shipped here.

mistral-common is a library of common utilities for Mistral AI models. It
provides the tokenizers (SentencePiece and Tekken), request/response
protocol data models, and validation helpers used to build prompts and
parse completions for Mistral models. This build enables the image extra
so multimodal image inputs can be processed.

Python mutation testing.

A tool to show calendar event details in Mutt.

python version of node-semver (https://github.com/isaacs/node-semver)

notify-py is a cross-platform desktop notification library for Python.

ormsgpack is a fast msgpack library for Python. It is a fork of orjson's
msgpack support and serializes faster than other Python msgpack libraries.
It supports serializing dataclasses, datetimes, numpy arrays and pydantic
models natively.